WebAI StudioBack to Demos
Screenshot → UI Code
Image InputDrop a UI screenshot and the multimodal model rebuilds it as HTML — rendered live next to the original.
Why On-Device?
Design mockups and internal screenshots are sensitive by default. On-device vision turns them into code without uploading a single pixel.
Interactive Demo
Prompt API (image): Loading...
Original Screenshot
Upload a UI screenshot, or use the sample mockup.
Rebuilt as HTML
The generated markup streams in here, then renders in a sandboxed iframe.
Implementation Code
demo.js
Keep exploring
56 demos, all running on-device.
Photo Semantic Search
Drop in your photos, and search them by meaning — "food on a table", "someone smiling" — without one pixel leaving your device.
Prompt API Semantic Embedder
Live Camera Q&A
Point your camera at anything, freeze a frame, and ask the on-device model about what it sees.
Prompt API
Draw & Guess
You sketch, Gemini Nano guesses: the model interprets your doodle after every stroke.
Prompt API